Subscribe
In East Africa, climate scientists are equipping traditional weather forecasting methods with artificial intelligence (AI) to make more accurate predictions of extreme weather events at minimal cost.
Climate change is one of the century’s biggest challenges for Africa. East Africa has increasingly become a frontline region battling the intensifying threat of extreme weather events, including droughts, floods and cyclones.
El Nino’s grip on East Africa led to widespread flooding, submerging entire areas in Uganda, Kenya and Tanzania, leaving behind a trail of destruction.
This was the first time Kenya experienced a cyclone. But the phenomenon has of late been common in the West Indian Ocean region, along the eastern and southern Africa coastline.
While Kenya only experienced mild effects of Cyclone Hidaya, Tanzania and its islands bore the brunt of the storm when the cyclone made landfall on May 4, 2024, as reported by the Kenya Meteorological Department (KMD) and the Tanzania Meteorological Authority (TMA).
With such great variations in weather, precise and timely forecasts are critical to safeguarding lives and livelihoods, said scientists from the University of Oxford.
The United Nations World Food Programme (WFP), Oxford University Physics Department, IGAD Climate Prediction and Applications Centre (ICPAC) and various national forecasting and meteorology agencies across East Africa are joining forces to pioneer a transformative initiative that is revolutionising extreme weather forecasting and early warning systems in the region.
Traditional weather forecasting methods have often been inadequate, failing to provide sufficient warning time and accuracy to effectively mitigate the impact of these disasters.
By combining physical atmospheric processes used in traditional forecasting with AI, scientists have developed a first-of-its-kind hybrid modeling approach to give more accurate rainfall forecasts without the need for expensive supercomputers.
This model, which only requires a laptop to run, gives local meteorological organisations a low-cost way of generating more accurate forecasts, in a region where precise observational data is often lacking.
The model is currently being rolled out in Kenya and Ethiopia. If successful in East Africa, researchers hope to replicate it in other parts of the world facing similar challenges.
ICPAC, which provides climate services for 11 countries in East Africa, will seek to scale the technology as well as build local ownership and trust, the authors mentioned in the report.